How to Use the NOAA Tides & Currents API MCP in LlamaIndex

Q: What's an example query for a LlamaIndex agent using the NOAA Tides & Currents API?

You could ask, "Compare today's water temperature from getwatertemperature with the indexed average for this week at station 9414290." The agent makes one live API call and queries its own index to form the comparison.

Turn live NOAA data into a queryable knowledge base with LlamaIndex. Ask questions about past and present tidal conditions.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NOAA Tides & Currents API MCP to LlamaIndex

Create your Vinkius account to connect NOAA Tides & Currents API to LlamaIndex and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup NOAA Tides & Currents API with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Tidal Data for Historical Context

Don't just get data, index it. Use a simple script to call `get_tide_predictions` and `get_water_levels` for a key shipping channel over the past year. LlamaIndex will ingest this data into a vector store, creating a searchable history of that station's behavior. Now your agent has memory. When you ask about an anomaly, it doesn't have to start from scratch. It can compare live data against the indexed history to give you context that a single API call never could.

Build RAG Apps on Live Maritime Conditions

Combine static documents with live API data. You can index your internal SOPs for port operations alongside real-time data from this MCP Server. Ask a question like, "Based on our procedures and today's water level, what's the go/no-go threshold?" Your LlamaIndex application will pull the procedure from your documents and the live depth from `get_water_levels`. The agent then synthesizes an answer grounded in both your rules and reality. It's a direct way to make your documents 'live'.

Query Your LlamaIndex Agent in Natural Language

Once the data is indexed, you can ask complex questions. For instance: "What was the biggest difference between predicted and actual high tide at station 8724580 last month?" Your agent queries the indexed results from `get_tide_predictions` and `get_water_levels` to find the answer. This turns raw API output into an actual knowledge base. It's perfect for building internal dashboards or research tools where you need to analyze trends over time, not just see a snapshot.

Setup guide

Set up NOAA Tides & Currents API MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all NOAA Tides & Currents API MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to NOAA Tides & Currents API tools.",
)
response = await agent.run("List recent NOAA Tides & Currents API data")

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by NOAA Tides & Currents. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect NOAA Tides & Currents API now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about NOAA Tides & Currents API MCP in LlamaIndex

LlamaIndex is built to index the output of tools. You can run `get_water_levels` every hour, and LlamaIndex will automatically add the results to a knowledge base. You can then query that history without making more API calls.

Yes. You can index your own files (like PDFs or text files) and the live output from NOAA tools into the same LlamaIndex data store. This lets you ask questions that require both sources to answer.

You could ask, "Compare today's water temperature from `get_water_temperature` with the indexed average for this week at station 9414290." The agent makes one live API call and queries its own index to form the comparison.

You write the script that calls the tools, and LlamaIndex handles turning the output into a queryable index. You decide how often to run `get_tide_predictions` or other tools to keep your knowledge base fresh.

The MCP Server handles the API call; it only sees the station ID and parameters you send. The data returned—like water level measurements and temperature readings—is then processed by your LlamaIndex application in your own environment. Vinkius doesn't see or store your indexed knowledge base.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript